alpr-unconstrained icon indicating copy to clipboard operation
alpr-unconstrained copied to clipboard

License Plate Detection and Recognition in Unconstrained Scenarios

Results 104 alpr-unconstrained issues
Sort by recently updated
recently updated
newest added

Hello , how can we implement percentage in the OCR recognition ? is it possible ? For example the plate is AA888BB percentage of correct is = 92.00

Hi @sergiomsilva, I would like to retrain the ocr-net model to add an extra separate class for both 0 and O - is this possible with your existing code, to...

Hi @sergiomsilva, do you include the code for your synthetic image generation? If not, can you please provide this? I am interested in generating synthetic Australian license plate images to...

when i use the train code,i change run.py p_model="models/my-trained-model/my-trained-model_final.h5" it has some problems , "mask_scale: Using default '1.000000' Loading weights from data/ocr/ocr-net.weights...Done! Performing OCR... rm: cannot remove '/tmp/output/*_lp.png': No such...

Hi, I was trying to implement the model in real time, sometimes, the detection for the number plate phase takes 0.1 second or less, but sometime it may need >1...

Hey, When I had given some test images..it's detecting N as M. Any idea about how it can be corrected? Btw great work!

Hi, I am having problems installing this repository. I use an AWS machine (Ubuntu Server 16.04 LTS (HVM), SSD Volume Type) I have installed Keras 2.2.4, TensorFlow 1.5.0, NumPy 1.14...

Hi I was wondering if i could use reconstruct method in such a way that i could provide crop licence plate to the function and get perspective corrected image as...

Hi, thanks for your work.Your work halped me a lot.I find a question during the inference process.During the inference process "reconstruct" function take a lot of time to run.I find...

if use image where number plate is too big in image. the model fail to detect it?